{"total":55,"rows":[{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793,"area":"mllm"},{"id":"2509.22186","title":"MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing","created":"2025-09-26","cited_by_count":116,"area":"mllm"},{"id":"2512.01989","title":"PAI-Bench: A Comprehensive Benchmark For Physical AI","created":"2025-12-01","cited_by_count":34,"area":"mllm"},{"id":"2605.12500","title":"SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture","created":"2026-05-12","cited_by_count":32,"area":"mllm"},{"id":"2508.13142","title":"Holistic Evaluation of Multimodal LLMs on Spatial Intelligence","created":"2025-08-18","cited_by_count":29,"area":"mllm"},{"id":"2505.11015","title":"WildDoc: How Far Are We from Achieving Comprehensive and Robust Document Understanding in the Wild?","created":"2025-05-16","cited_by_count":26,"area":"mllm"},{"id":"2503.02358","title":"Are Large Vision Language Models Good Game Players?","created":"2025-03-04","cited_by_count":19,"area":"mllm"},{"id":"2505.21333","title":"MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video Scenarios","created":"2025-05-27","cited_by_count":18,"area":"mllm"},{"id":"2504.00414","title":"Multimodal LLMs for OCR, OCR Post-Correction, and Named Entity Recognition in Historical Documents","created":"2025-04-01","cited_by_count":12,"area":"mllm"},{"id":"2506.20168","title":"Seeing is Believing? Mitigating OCR Hallucinations in Multimodal Large Language Models","created":"2025-06-25","cited_by_count":12,"area":"mllm"},{"id":"2506.12776","title":"Native Visual Understanding: Resolving Resolution Dilemmas in Vision-Language Models","created":"2025-06-15","cited_by_count":11,"area":"mllm"},{"id":"2502.16586","title":"Multimodal Large Language Models for Text-rich Image Understanding: A Comprehensive Review","created":"2025-02-23","cited_by_count":9,"area":"mllm"},{"id":"2512.02895","title":"MindGPT-4ov: An Enhanced MLLM via a Multi-Stage Post-Training Paradigm","created":"2025-12-02","cited_by_count":9,"area":"mllm"},{"id":"2603.24373","title":"PP-OCRv5: A Specialized 5M-Parameter Model Rivaling Billion-Parameter Vision-Language Models on OCR Tasks","created":"2026-03-25","cited_by_count":9,"area":"mllm"},{"id":"2511.04727","title":"IndicVisionBench: Benchmarking Cultural and Multilingual Understanding in VLMs","created":"2025-11-06","cited_by_count":8,"area":"mllm"},{"id":"2602.04802","title":"VISTA-Bench: Do Vision-Language Models Really Understand Visualized Text as Well as Pure Text?","created":"2026-02-04","cited_by_count":8,"area":"mllm"},{"id":"2606.10400","title":"Do Vision-Language Models See or Guess? Measuring and Reducing Textual-Prior Reliance with a Phrasing-Controlled Benchmark","created":"2026-06-09","cited_by_count":8,"area":"mllm"},{"id":"2603.18472","title":"Cognitive Mismatch in Multimodal Large Language Models for Discrete Symbol Understanding","created":"2026-03-19","cited_by_count":7,"area":"mllm"},{"id":"2511.21750","title":"SO-Bench: A Structural Output Evaluation of Multimodal LLMs","created":"2025-11-23","cited_by_count":6,"area":"mllm"},{"id":"2505.14381","title":"SCAN: Semantic Document Layout Analysis for Textual and Visual Retrieval-Augmented Generation","created":"2025-05-20","cited_by_count":5,"area":"mllm"},{"id":"2507.11932","title":"Hyperphantasia: A Benchmark for Evaluating the Mental Visualization Capabilities of Multimodal LLMs","created":"2025-07-16","cited_by_count":5,"area":"mllm"},{"id":"2602.07038","title":"UNIKIE-BENCH: Benchmarking Large Multimodal Models for Key Information Extraction in Visual Documents","created":"2026-02-03","cited_by_count":5,"area":"mllm"},{"id":"2608.15045","title":"MOSS-VL Technical Report","created":"2026-08-15","cited_by_count":5,"area":"mllm"},{"id":"2512.01248","title":"TRivia: Self-supervised Fine-tuning of Vision-Language Models for Table Recognition","created":"2025-12-01","cited_by_count":4,"area":"mllm"},{"id":"2607.24957","title":"PerceptionBench: Evaluating Atomic Visual Perception in Multimodal Large Language Models","created":"2026-07-27","cited_by_count":4,"area":"mllm"},{"id":"2605.18852","title":"Robust Checkpoint Selection for Multimodal LLMs via Agentic Evaluation and Stability-Aware Ranking","created":"2026-05-13","cited_by_count":3,"area":"mllm"},{"id":"2502.18512","title":"FCoT-VL:Advancing Text-oriented Large Vision-Language Models with Efficient Visual Token Compression","created":"2025-02-22","cited_by_count":2,"area":"mllm"},{"id":"2503.23667","title":"Context-Independent OCR with Multimodal LLMs: Effects of Image Resolution and Visual Complexity","created":"2025-03-31","cited_by_count":2,"area":"mllm"},{"id":"2509.12278","title":"PATIMT-Bench: A Multi-Scenario Benchmark for Position-Aware Text Image Machine Translation in Large Vision-Language Models","created":"2025-09-14","cited_by_count":2,"area":"mllm"},{"id":"2511.14998","title":"FinCriticalED: A Visual Benchmark for Financial Fact-Level OCR","created":"2025-11-19","cited_by_count":2,"area":"mllm"},{"id":"2604.04411","title":"Responses Fall Short of Understanding: Revealing the Gap between Internal Representations and Responses in Visual Document Understanding","created":"2026-04-06","cited_by_count":2,"area":"mllm"},{"id":"2604.12978","title":"GlotOCR Bench: OCR Models Still Struggle Beyond a Handful of Unicode Scripts","created":"2026-04-14","cited_by_count":2,"area":"mllm"},{"id":"2607.21617","title":"Do VLMs Read or Rewrite? On Transcription Faithfulness in Vision-Language Models","created":"2026-05-29","cited_by_count":2,"area":"mllm"},{"id":"2609.02401","title":"CA-OPD: Confidence-Aware On-Policy Distillation for Structured Visual Prediction","created":"2026-09-02","cited_by_count":2,"area":"mllm"},{"id":"2602.11960","title":"Benchmarking Vision-Language Models for French PDF-to-Markdown Conversion","created":"2026-02-12","cited_by_count":1,"area":"mllm"},{"id":"2602.21053","title":"OCR-Agent: Agentic OCR with Capability and Memory Reflection","created":"2026-02-24","cited_by_count":1,"area":"mllm"},{"id":"2603.22165","title":"ACPO: Counteracting Likelihood Displacement in Vision-Language Alignment with Asymmetric Constraints","created":"2026-03-23","cited_by_count":1,"area":"mllm"},{"id":"2605.19929","title":"Breaking Modality Heterogeneity in Low-Bit Quantization for Large Vision-Language Models","created":"2026-05-19","cited_by_count":1,"area":"mllm"},{"id":"2607.02991","title":"GuideMe: Multi-Domain Task Guidance and Intervention in Streaming Video","created":"2026-07-03","cited_by_count":1,"area":"mllm"},{"id":"2607.22708","title":"StepX-Edge: An On-Device UI Vision-Language Model via Architecture-Training-Deployment Co-Design","created":"2026-07-20","cited_by_count":1,"area":"mllm"},{"id":"2608.01979","title":"ET-Prune: Evidence-Aware Dynamic Budgeting for Visual Token Pruning in Text-Rich MLLMs","created":"2026-08-03","cited_by_count":1,"area":"mllm"},{"id":"2609.27948","title":"VIVAS: Vitalizing Visual Perception in VLM Pre-training via Vision-language Unified Autoregressive Supervision","created":"2026-08-25","cited_by_count":1,"area":"mllm"},{"id":"2505.10055","title":"PsOCR: Benchmarking Large Multimodal Models for Optical Character Recognition in Low-resource Pashto Language","created":"2025-05-15","cited_by_count":0,"area":"mllm"},{"id":"2601.10305","title":"DanQing: An Up-to-Date Large-Scale Chinese Vision-Language Pre-training Dataset","created":"2026-01-15","cited_by_count":0,"area":"mllm"},{"id":"2601.21342","title":"Ostrakon-VL: Towards Domain-Expert MLLM for Food-Service and Retail Stores","created":"2026-01-29","cited_by_count":0,"area":"mllm"},{"id":"2603.27942","title":"JaWildText: A Benchmark for Vision-Language Models on Japanese Scene Text Understanding","created":"2026-03-30","cited_by_count":0,"area":"mllm"},{"id":"2605.17093","title":"HEED: Density-Weighted Residual Alignment for Hybrid Vision-Language Model Distillation","created":"2026-05-16","cited_by_count":0,"area":"mllm"},{"id":"2606.01393","title":"Dr. DocBench: A Comprehensive Benchmark for Expert-Level and Difficult Document Parsing","created":"2026-05-31","cited_by_count":0,"area":"mllm"},{"id":"2606.07641","title":"Readable Yet Unpredictable: Rotated-Outcome Prediction in Vision-Language Models","created":"2026-06-01","cited_by_count":0,"area":"mllm"},{"id":"2606.09435","title":"MUDIDI: A Two-Stage Framework for Multilingual Dictionary Digitization with Language Models","created":"2026-06-08","cited_by_count":0,"area":"mllm"},{"id":"2607.03624","title":"RADIO1D: Elastic Representations for Condensed Vision Modeling","created":"2026-07-03","cited_by_count":0,"area":"mllm"},{"id":"2608.20122","title":"ArmorOCR: Grounded Adversarial Visual Perception via Observation-Transferred Self-Distillation","created":"2026-08-20","cited_by_count":0,"area":"mllm"},{"id":"2609.34781","title":"When VLMs Trust Context: Evaluating Scene Text Recognition under Misleading Context","created":"2026-09-28","cited_by_count":0,"area":"mllm"},{"id":"2610.11148","title":"SP-DocReader: Difference-Aware Self-Play for Precise Document OCR","created":"2026-10-08","cited_by_count":0,"area":"mllm"},{"id":"2610.14397","title":"RealityBench: Simulated Environments to Evaluate a Vision Language Model's Ability to Document Human Physical Work","created":"2026-10-09","cited_by_count":0,"area":"mllm"}],"next_cursor":null}